GHSA-vv2h-2w3q-3fx7

PandasAI interactive prompt function Remote Code Execution (RCE)

Source: GitHub Advisory Database (reviewed) Critical CVE-2024-12366

Packages

Ecosystem	Package	Affected	Fixed in
PyPI	pandasai	<= 2.4.2	no fix listed

Details

As written in the advisory (Markdown source, shown as plain text).

PandasAI uses an interactive prompt function that is vulnerable to prompt injection and run arbitrary Python code that can lead to Remote Code Execution (RCE) instead of the intended explanation of the natural language processing by the LLM. The security controls of PandasAI (2.4.3 and earlier) fail to distinguish between legitimate and malicious inputs, allowing the attackers to manipulate the system into executing untrusted code, leading to untrusted code execution (RCE), system compromise, or pivoting attacks on connected services.

References

External links from the advisory. They lead to third-party sites.

https://nvd.nist.gov/vuln/detail/CVE-2024-12366 advisory
https://docs.getpanda.ai/v3/privacy-security web
https://docs.pandas-ai.com/advanced-security-agent web
https://github.com/sinaptik-ai/pandas-ai package
https://www.kb.cert.org/vuls/id/148244 web